agentleFS
dkadtsdkadts/landing-kit-building/.claude/skills/brief/SKILL.md

brief

Skill2 starsChanged 3 months agoMITView on GitHub

Interactive survey across the 9 brief files. Starts with desktop-first vs mobile-first (the most important question), then niche, then the rest. Fills brief/*.md instead of the user.

81 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture, strategy and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • toneron2Skill

    capture

    Capture thoughts to inbox with automatic classification

    Also in 6 projects that use this

  • EpistatesSkill

    strategy

    Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.

    Also in 4 projects that use this

  • aleksander-dytkoSkill

    decision

    Make a product decision with full context from the vault and available sources

    Also in 3 projects that use this

  • dirienSkill

    decide

    Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.

    Also in 5 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 7 projects that use this

  • howellsSkill

    reconcile

    Audit a project against current plugin conventions and offer to update structure.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. 0 are common, 7 are distinctive, and 10 are very specific to this project.

  • 0

    Common

    Most of the 74 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 10

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start of a new project (before any /build).

    line 12
  2. Very specific:

    Read every brief/*.md. Determine which fields are filled, which are TBD.

    line 19
  3. Very specific:

    Wait for an explicit answer.

    line 34
  4. Distinctive:

    Ask one question at a time (do not batch 10 questions at once — user tires).

    line 40
  5. Distinctive:

    Use checklists where preset options exist.

    line 41
  6. Very specific:

    Do not accept "beauty" — narrow it to "men's Botox for CEOs 35-50 in Barcelona".

    line 47
  7. Very specific:

    Do not accept "clients" — narrow maturity (cold/warm/hot).

    line 48
  8. Very specific:

    If the user checked interactive blocks — offer to run /blocks immediately to configure.

    line 52
  9. Distinctive:

    If TBD remain — what to ask the client.

    line 57
  10. Distinctive:

    One field — one question: Do not batch.

    line 61
  11. Distinctive:

    Do not guess for the user: If unclear — clarify.

    line 62
  12. Distinctive:

    Save as you go: Not at the end. Otherwise if the session drops — everything's lost.

    line 64
  13. Distinctive:

    Respect status: If a field is already filled — do not re-ask, only clarify if needed.

    line 65
  14. Very specific:

    Do not start /design-lock until 01-business + 02-audience + 05-design are filled.

    line 69
  15. Very specific:

    Do not suggest skipping 00-priority — it's critical.

    line 70
  16. Very specific:

    Do not fill brief/copy-analysis.md — that's /copy-analyze.

    line 71
  17. Very specific:

    Do not touch brief/blocks/*.md — that's /blocks.

    line 72

“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/brief

Guides the user through the questionnaire. Fills brief/00-priority.md → brief/08-content-pipeline.md.

When to use

  • Start of a new project (before any /build).
  • User prefers a dialog over filling .md files by hand.
  • Revising an existing brief.

Process

Step 1. Read existing files Read every brief/*.md. Determine which fields are filled, which are TBD.

Step 2. Ask the first — most important — question

Desktop-first or mobile-first?

This decides:
- Assembly order (down or up)
- Block composition
- Reference viewport (1920px or 390px)

Help to choose: <brief decision table from 00-priority.md>

Wait for an explicit answer. Save to brief/00-priority.md.

Step 3. Walk files 01-08 in order

For each file:

  • List TBD fields.
  • Ask one question at a time (do not batch 10 questions at once — user tires).
  • Use checklists where preset options exist.
  • Save the answer (Edit tool).

Step 4. Special attention — niche discovery

brief/01-business.md — niche section — critical for /copy-analyze. Do not accept "beauty" — narrow it to "men's Botox for CEOs 35-50 in Barcelona". Do not accept "clients" — narrow maturity (cold/warm/hot).

Step 5. After 07-interactive

If the user checked interactive blocks — offer to run /blocks immediately to configure.

Step 6. Final summary

Show brief completeness: how many fields LOCKED, how many TBD. If TBD remain — what to ask the client.

Rules of behavior

  • One field — one question. Do not batch.
  • Do not guess for the user. If unclear — clarify.
  • Use examples. "e.g. form submission → manager calls within 2 hours".
  • Save as you go. Not at the end. Otherwise if the session drops — everything's lost.
  • Respect status. If a field is already filled — do not re-ask, only clarify if needed.

What NOT to do

  • Do not start /design-lock until 01-business + 02-audience + 05-design are filled.
  • Do not suggest skipping 00-priority — it's critical.
  • Do not fill brief/copy-analysis.md — that's /copy-analyze.
  • Do not touch brief/blocks/*.md — that's /blocks.

Next

Once done:

  • Suggest /inbox (if the client already has materials) or wait for materials.
  • Or /refs (if references are already in references/).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.